Five real anchors. Five different reads.
Pick an anchor below. See the classification flags decision_brief returned, then read what an agent does with them — in plain English.
Real responses from POST /api/v1/decision_brief captured 2026-05-13. Flag values + raw numbers are the actual production output; prose is what an agent reading those flags would write in its own voice.
Honestly, this one reads like a coin flip. NVDA’s in-regime analogs printed about the same as everything else — no real edge in either direction.
21 closest analogs that printed in the same regime (high vol, tech lagging, news on the tape) returned a +0.09% median over 5 days at a 52% hit rate. The other 111 regimes printed +0.27% on the same hit rate. The regime isn’t doing much work here either way.
- ·Sector lagging hard. XLK 60-day RS is −10.4 — skews tech reads lower until it turns.
- ·News without conviction. Pulse is +0.11 with the tape active — looks like vol repricing, not a real narrative change.
- ·Earnings in 16 sessions. Pattern reads tend to weaken this close to the print.
Bottom line: No meaningful edge, low conviction. In-regime sample is soft (n=21) and the vol regime was derived — treat this as a lean, not a thesis.
Want to ask your own anchor?
Drop the MCP server into Claude, ChatGPT, or Cursor and ask anything. 200 free calls a day. No card.